{"id":"W2765441486","doi":"10.2196/medinform.8531","title":"Ranking Medical Terms to Support Expansion of Lay Language Resources for Patient Comprehension of Electronic Health Record Notes: Adapted Distant Supervision Approach","year":2017,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Heart, Lung, and Blood Institute; National Institutes of Health; U.S. Department of Veterans Affairs","keywords":"Computer science; Ranking (information retrieval); Comprehension; Natural language processing; Annotation; Domain (mathematical analysis); Artificial intelligence; Unified Medical Language System; Vocabulary; Resource (disambiguation); Information retrieval; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002206086,0.001308265,0.0007326416,0.002749219,0.0007216505,0.0008119267,0.001404184,0.001107309,0.004111235],"category_scores_gemma":[0.01103699,0.0003106152,0.0009609213,0.001084713,0.0007451681,0.002030393,0.002120342,0.001854844,0.00168428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009872927,"about_ca_system_score_gemma":0.002193115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006497989,"about_ca_topic_score_gemma":0.01125649,"domain_scores_codex":[0.9980385,0.0006856869,0.0001632199,0.0006086636,0.00038015,0.0001238701],"domain_scores_gemma":[0.9944044,0.002756642,0.0003932533,0.0005519126,0.001639257,0.0002545689],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001231789,0.0009133554,0.01538612,0.0006991438,0.0001319632,0.0004128418,0.001121101,0.0283788,0.04185149,0.003696488,0.02718581,0.8789911],"study_design_scores_gemma":[0.0002852559,0.0008053517,0.01197114,0.0001334864,0.0001722604,0.0004600266,0.0008102095,0.9181198,0.04049315,0.01263754,0.01400172,0.0001100462],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3248538,0.001518855,0.6425581,0.001820543,0.0002208,0.001083985,0.00340115,0.01540663,0.009136196],"genre_scores_gemma":[0.6646668,0.0002555663,0.3200165,0.0004174644,0.0001703441,0.0004204306,0.008936523,0.0003524784,0.004763859],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006497989,"threshold_uncertainty_score":0.01375341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.024468093395207,"score_gpt":0.3400213850010245,"score_spread":0.3155532916058175,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}